Predicting Ethereum Fraudulency using ChaosNet

Abstract

Abstract Cryptocurrencies are in high demand right now, perhaps because of their volatile nature and untraceable difficulties. Bitcoin, Ethereum, Dogecoin, and others are just a few. This research seeks to identify falsehoods and probable fraudulences in Ethereum transactional processes. We have provided this capability to ChaosNet, an Artificial Neural Network constructed using Generalized Luroth Series maps. At many spatiotemporal scales, Chaos has been objectively discovered in the brain. Several synthetic neuronal simulations, including the Hindmarsh-Rose model, possess Chaos, and individual brain neurons are known to display chaotic bursting phenomenon. Although Chaos is included in several Artificial Neural Networks (ANNs), for instance, the Recursively Generating Neural Networks, no ANN exist for classical tasks that is fully made up of Chaoticity. ChaosNet uses the chaotic GLS neurons' topological transitivity property to perform classification problems with cutting-edge performance the pool of data including lower training sample count. This synthetic neural network can perform categorization tasks by gathering from a definite amount of training data. ChaosNet utilizes some of the best traits of network subjected to biological neurons, which derive from the strong Chaotic activity of individual neurons, to solve difficult classification tasks on par with or better than standard Artificial Neural Networks. It has been shown to require much fewer training samples.